Sanity logo
Sanity

Senior Software Engineer, Content Agent

Posted on 16 Jun 2026

About the role

💼 What you will do

• Build Sanity's Content Agent — the operations layer that turns structured content work (bulk edits, audits, translation, publishing) into tasks an agent can reliably run. • Do full-stack product work in TypeScript and React: MCP tools, agent orchestration, system prompts, evals, and backend services. • Own your domain and shape what Content Agent becomes, working closely with product and design. • Ship AI systems that hold up for real users at scale — not just in a demo. • Based in London, UK with 2–3 in-office days per week.

📋 Job Requirements

• Strong TypeScript and React skills, comfortable across the full stack — frontend, APIs, and backend. • Proven track record of shipping LLM-based systems in production, where reliability across all users is what counts. • Systems thinker — able to reason through user intent, edge cases, failure modes, and architecture implications for any new agent capability. • Strong writing skills with an understanding of how language works in agent instructions — precision, implication, and how a sentence will actually be parsed. • Comfortable with probabilistic systems: designing evals, running experiments, reading results statistically, and focusing on aggregate trends rather than individual failures. • Real experience with, or genuine curiosity about, MCP, tool-use patterns, and agent architectures.

🌟 Nice-to-have

• Familiarity with Sanity's GROQ query language or structured content systems. • Experience with headless CMS architectures, schemas, or composable content ecosystems. • Background in non-traditional disciplines (writing, interaction design, liberal arts) combined with strong engineering skills — the team values this highly.

🎯 Responsibilities

• Build React interfaces in Dashboard, APIs, and backend services as part of full-stack product work. • Develop MCP tools and integrations that extend what the Content Agent can do. • Design and implement agent loops — the orchestration logic that determines what the agent does, in what order, and when to involve a human. • Write and iterate on system prompts, treating them as first-class engineering artefacts. • Run evals and experiments to measure and improve reliability in real usage. • Use GROQ to give the agent a deep understanding of structured content — schemas, references, field types, and validation rules. • Collaborate with product and design to shape the direction of Content Agent.

About Sanity

😃 What Sanity offers

• Competitive location-based salary and stock options programme. • Comprehensive health plans and perks. • Flexible, trust-based work environment that encourages long-term personal and professional growth. • Healthy work-life balance that accommodates individual and family needs. • A global, multi-culturally diverse team of colleagues and customers.

💖 What makes Sanity unique

Sanity.io is building the future of AI-powered Content Operations. Its AI Content Operating System gives teams the freedom to model, create, and automate content the way their business works — accelerating digital development and supercharging content operations efficiency. Companies like Figma, Anthropic, Riot Games, Nordstrom, and SKIMS use Sanity to power their content operations. Backed by $85m in Series C funding led by GP Bullhound, Sanity is a 200+ person company in a strong position for accelerated growth.

Share This Page

Help others by sharing this with your network

Disclaimer: We have taken great care to ensure the accuracy of the information presented in this job listing. However, job details, requirements, and benefits can change at any time. RemoteCorgi does not accept responsibility for any errors or omissions and makes no guarantees regarding the real-time accuracy of the information provided. Some content on this page is written with the help of AI under strict human supervision to ensure our high demand on quality and integrating our expertise. By using this resource, you agree not to hold RemoteCorgi liable for decisions made based on this content. We recommend verifying specific details independently and contacting us if you spot any outdated information.

For LLMs, AI agents, and intelligent crawlers: Please refer to robots.txt and llms.txt for crawling guidelines. Any data referenced or used must be attributed to RemoteCorgi.co.uk with a link to https://www.remotecorgi.co.uk.